snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-07-29 09:39:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make all search tests pass, fix distinctAttribute bug

Browse Source
This commit is contained in:
Loïc Lecrenier
2023-04-24 12:11:25 +02:00
parent a7a0891210
commit d1fdbb63da
17 changed files with 465 additions and 327 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/search/new/ranking_rule_graph/position/mod.rs
View File

@ -56,8 +56,13 @@ impl RankingRuleGraphTrait for PositionGraph {
}
for phrase in term.term_subset.all_phrases(ctx)? {
for &word in phrase.words(ctx).iter().flatten() {
let positions = ctx.get_db_word_positions(word)?;
// Only check the position of the first word in the phrase
// this is not correct, but it is the best we can do, since
// it is difficult/impossible to know the expected position
// of a word in a phrase.
// There is probably a more correct way to do it though.
if let Some(word) = phrase.words(ctx).iter().flatten().next() {
let positions = ctx.get_db_word_positions(*word)?;
all_positions.extend(positions);
}
}

24
milli/src/search/new/ranking_rule_graph/proximity/compute_docids.rs
View File

@ -79,11 +79,6 @@ pub fn compute_docids(
//
// This is an optimisation to avoid checking for an excessive number of
// pairs.
// WAIT, NO.
// This should only be done once per node.
// Here, we'll potentially do is.. 16 times?
// Maybe we should do it at edge-build time instead.
// Same for the future attribute ranking rule.
let right_derivs = first_word_of_term_iter(ctx, &right_term.term_subset)?;
if right_derivs.len() > 1 {
let universe = &universe;
@ -190,11 +185,6 @@ fn compute_non_prefix_edges(
docids: &mut RoaringBitmap,
universe: &RoaringBitmap,
) -> Result<()> {
let mut used_left_phrases = BTreeSet::new();
let mut used_right_phrases = BTreeSet::new();
let mut used_left_words = BTreeSet::new();
let mut used_right_words = BTreeSet::new();
let mut universe = universe.clone();
for phrase in left_phrase.iter().chain(right_phrase.iter()).copied() {
@ -204,25 +194,19 @@ fn compute_non_prefix_edges(
return Ok(());
}
}
if let Some(left_phrase) = left_phrase {
used_left_phrases.insert(left_phrase);
}
if let Some(right_phrase) = right_phrase {
used_right_phrases.insert(right_phrase);
}
if let Some(new_docids) =
ctx.get_db_word_pair_proximity_docids(word1, word2, forward_proximity)?
{
let new_docids = &universe & new_docids;
if !new_docids.is_empty() {
used_left_words.insert(word1);
used_right_words.insert(word2);
*docids |= new_docids;
}
}
if backward_proximity >= 1
// no swapping when either term is a phrase
// TODO: for now, we don't do any swapping when either term is a phrase
// but maybe we should. We'd need to look at the first/last word of the phrase
// depending on the context.
&& left_phrase.is_none() && right_phrase.is_none()
{
if let Some(new_docids) =
@ -230,8 +214,6 @@ fn compute_non_prefix_edges(
{
let new_docids = &universe & new_docids;
if !new_docids.is_empty() {
used_left_words.insert(word2);
used_right_words.insert(word1);
*docids |= new_docids;
}
}